Identifying contact center agents based upon biometric characteristics of an agent's speech

Abstract

The present invention discloses a contact center with speaker identification and verification (SIV) capabilities. In the invention, a set of contact center components can provide automated interactive communications with callers, can provide queue management for callers waiting to communicate with live agents, and can provide skills based routing for assigning live agents to callers. The SIV component can analyze speech utterances to determine a speaker identify based upon biometric characteristics of the analyzed speech utterances. Additionally, the SIV component can process speech from contact center sessions. In one embodiment, the SIV component can prevent agent substitutions from occurring of which the call center is unaware. The SIV component can also be used to distinguish whether communication session content was spoken by a contact center agent or a caller.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS[0001]This continuation-in-part application claims the benefit of U.S. patent application Ser. No. 11 / 680,304 filed 28 Feb. 2007, which is hereby incorporated by reference herein.BACKGROUND[0002]1. Field of the Invention[0003]The present invention relates to the field of contact center technologies and, more particularly, identifying contact center agents based upon biometric characteristics of an agent's speech[0004]2. Description of the Related Art[0005]Historically, contact center agents have been placed in operations centers where they work along side many other contact center agents. Each agent has operated from an agent-specific desktop, which includes a data terminal and phone connection. Contact center agents have been identified based upon a user name and password combination and / or based upon an identifier of a device (e.g., phone or terminal) used by the agent.[0006]Conventionally, front end software that drives the agent desktop has...

AI Technical Summary

Benefits of technology

[0012]In another example, SIV techniques can be used to automatically distinguish a caller's utterances from those of a contact center agent. One use of this technique is to automatically determine if an inappropriate phrase, such as cursing, was uttered by an agent (who can be disciplined for cursing) or a caller. Another use can be to increase speaker identification accuracy for transcription purposes.

[0013]The present invention can be implemented in accordance with numerous aspects consistent with the material presented herein. For example, one aspect of the present invention can include a contact center including a set of contact center components and a SIV component. The contact center components can provide automated interactive communications with callers, can provide queue management for callers waiting to communicate with live agents, and can provide skills based routing for assigning lie agents to callers. The SIV component can analyze speech utterances to determine a speaker identify based upon biometric characteristics of the analyzed speech utterances. Additionally, the SIV component can process speech from contact center sessions to automatically identify at least one contact center agent involved in each of the contact center sessions. In one embodiment, the SIV component can be repetitively used to prevent agent substitutions from occurring of which the call center is unaware. In another embodiment, the SIV component can be used to distinguish whether communication session content was spoken by a contact center agent or a caller. Speaker determination can be important for transcriptions, for detecting an origin of inappropriate phrases (e.g., cursing), and other purposes.

Problems solved by technology

The protocols, hardware, and software used by the different vendors have historically been incompatible with one another, requiring all contact center components to be those of a single vendor.

Conventional agent identifying techniques lack a fraud resistant means of identifying an agent.

Callers, and / or the call center would remain unaware of the substitution, which could result in an unqualified or untrained call center agent handling customer issues.

Images